跳到正文
Hacker News:AI 熱帖·· 5 天前AI 評分46

OpenCode Browse:Hacker News 用戶討論瀏覽器控制方案

OpenCode Browse

AI 導讀

Hacker News 用戶討論 OpenCode Browse,並有人建議以 Chrome DevTools Protocol(CDP)控制瀏覽器,再透過 JSON-RPC 封裝成 MCP API。部分用戶批評 OpenCode V2 的安全模型及升級方式,另有用戶表示未有同樣觀感,並提到自己使用 OpenCode 的情況有限。

正文

Image 1Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

OpenCode Browse (opencode.ai) 116 points by mfiguiere4 hours ago | hide | past | favorite | 53 comments help Image 2testtestmetest2 hours ago | next[–] Opencode vibe codes and releases like 3 projects a week at this points. Cool, just know its throwaway software to them. They seem really reckless when it comes to security. Opencode V2 basically threw security out the window. Theyve completely lost the plot as an org. Their CEO spends all day on twitter talking about how much better he is than everyone. And how nobody can use agents like he can. Its quite obnoxious Also just use CDP, way too many browser solutions for agents when chrome ships with the ability to control the browser at a low level. If you want to wrap it in a jsonrpc api for mcp, this is like 4 hrs or a work for an llm, point them at a pkg thats uses CDP like go-rod. reply Image 3gexla32 minutes ago | parent | next[–] > Their CEO spends all day on twitter talking about how much better he is than everyone. And how nobody can use agents like he can. Its quite obnoxious I follow him on X, and I never got that impression. He has always come across as a skeptic IMO. Often wondering what others know that he doesn't due to practices that he hasn't found useful. I think yesterday he posted something suggesting that he doesn't follow usage patterns posted by others because the models have advanced to the point where any perceived improvements are by model rather than these patterns. I generally agree with this, and try not to get attached to any way of working with these things. As for the usage of OpenCode, I have kept it to a minimum. V1 memory usage got a bit wild. Not sure if V2 has greatly improved. I have signed up for their Go plan a few times for times when I get tight on my other subs. reply Image 4julianeon8 minutes ago | parent | prev | next[–] I'm glad you made that comment because I didn't look very closely at the URL and thought this was an OpenAI product. reply Image 5liuliu2 hours ago | parent | prev | next[–] Their marketing is very effective. And marketing is the only thing matters in software industry going forward. Making good software is not. reply Image 6ijidak40 minutes ago | root | parent | next[–] Interesting. Where do you see their marketing that impresses you? I mainly read Hacker News. So not surprised I've missed it. But, I'm curious because I love to study good marketing. reply Image 7davmar1 hour ago | parent | prev | next[–] These guys have been building amazing and useful products for years. SST was a tool ahead of its time when it launched (I used it). It’s on version 3 and is now open source and community maintained. I’ve found it useful. The OpenCode agent is very cool and they even host some of their own models via a subscription. I found it useful too. I haven’t used this new one yet. Have you built anything useful, or are you just a critic? reply Image 8testtestmetest1 hour ago | root | parent | next[–] You sound biased for someone who's hardly used the product. Yes I put in 12 hrs a day, and usually running overnight as well in maybe half a dozen containers. I have billions of tokens going through Opencode a day as my main harness, for atleast a year. I cannot accept their security model in V2 nor am I willing accept the nightmare and dangerous process of an upgrade. Where they basically tell the user, it ships with no permission model your plugins wont work, and we're making arbitrary changes all the time because we dont like how something is spelt/is plural that break your config. Typical vibe coded changes that are made for no rhyme or reason that are pushed without care so the user deal with the headache. V2 is literaly slop because they got obsessed with full on vibe coding. Instead of having a version bump to V2 that cared about backwards compatibility they said screw the user, we have llms now just tell it to upgrade your config and ask it to make no mistakes, we provided a skill, good luck (oh, and by the way we no longer ship an easy way to confine the agent into a directory, thats on you good luck.. Ask the llm who now has access to your entire computer, make no mistakes). This wouldnt be that big of a deal if I didnt have half a dozen different sets of configs with granular permissions, each with their own plugins for different clients Im working for. Its probably a multi day task to upgrade for any power user which shouldn't be the case for any piece of software's version bump. If Im going to take the time to upgrade it would be to a different harness all together. Oh and by the way, when you turn off acess to the internet to a container and use a local model, session titles suddenly stop working.. Turn it back on and they start working even with no Opencode acct authenticated, because they're summarizing your conversations without your consent to derive session titles.... So who knows what they're swallowing up of your conversation data idk, I should put it behind an burp and see. They have 2k issues on github but are shipping native UI frameworks nobody is going to use, for twitter likes. They got a bunch of their users keys stolen and never took responsibility but rather blamed it on "distillers" instead of their own internal policies that lead to it. You can thank Dax for how every AI company scapegoats all their failures to distillers now whenever they fumble your credentials. reply Image 9willis9369 minutes ago | root | parent | next[–] This is pretty alarming. I try to set up my containers to only have web access via specific provider MCPs and not just free reign to the open web. I would not want to use a harness trying to fight against me on what is already a very hard problem. reply Image 10arcanemachiner1 hour ago | parent | prev | next[–] > Also just use CDP, way too many browser solutions for agents when chrome ships with the ability to crontrol the browser at a low level. > If you want to wrap it in a jsonrpc api for mcp, this is like 4 hrs or a work for an llm, point them at a pkg thats uses CDP like go-rod. As someone who has vibe-coded my own such wrapper, I think that there is a lot of value in having a common interface for an agent to interact with CDP beyond just slinging together ad-hoc scripts until something works. CDP exposes a lot of features, but exposing them to an agent in a sane, consistent way takes a good bit of work. It's also taken me a good bit longer than 4 hours by now. The features really add up over time. reply Image 11esperent1 hour ago | root | parent | next[–] I use playwright-cli any a skill that's about 150 lines. Seems to have been working well for about 6 months now. reply Image 12testtestmetest1 hour ago | root | parent | prev | next[–] Took me about half a day. Granted, Ive neen building browser automation tools on top of cdp for many years now. reply Image 13sebws2 hours ago | parent | prev | next[–] They also seem to have abandoned their pre-OpenCode success SST with no acknowledgement to paying customers. reply Image 14OG_BME2 hours ago | parent | prev | next[–] He's not the CEO (although everyone thinks he is) reply Image 15testtestmetest1 hour ago | root | parent | next[–] He runs Opencode and major stakeholder in the parent company. They don't too publish an org chart. Just because you dont give yourself the the Chief Executive title doesn't mean you aren't the Chief executive. Thr not a ceo thing is kind of a twitter meme too, hes the guy in charge. reply Image 16ProphetOfParado2 hours ago | parent | prev | next[–] > Their CEO spends all day on twitter talking about how much better he is than everyone. Not that agreement proves anything but I am glad to know I was not the only one. Him, Boris, Theo (t3.gg or something) -- I look at their archetype and wonder if that is what you need for success and if indeed that is what you need, then perhaps I do not want success at all. reply Image 17alasano2 hours ago | root | parent | next[–] It's interesting because it's not strictly speaking needed. You have people who have high visibility on social media without playing games or constantly exaggerating their accomplishments or work. But you're right that people who do play these games and adopt your so called archetype end up with this much visibility. I think the reality is as simple as grandiose claims or presentation or just being clickbait personified works to gain an audience. It's also why these people have a bigger ratio of fans to people who can't stand them. The much rarer people who reach a large audience while remaining genuine tend to be much more universally liked. The ratio is better for sure at least. reply Image 18doctaj1 hour ago | root | parent | prev | next[–] No, they just all know how to game the different socials and they do, even if it's obnoxious or cringe. reply Image 19jareklupinski2 hours ago | root | parent | prev | next[–] > if indeed that is what you need, then perhaps I do not want success at all. what would success bring you? if what you want is success at all costs however, that is where you have to start reply Image 20slopinthebag2 hours ago | root | parent | prev | next[–] it's been this way for years tbh. they made the whole web scene insufferable. the few gems have remained in the web scene, while everyone else moved to ai. reply Image 21algo_trader2 hours ago | parent | prev | next[–] > Opencode V2 basically threw security out the window Yes. I was shocked to suddenly discover everything was "auto permit all" Then i discovered that all my pinned sessions were lost Then you read on X that they vibing some sort of UI library or whatever the flavour of the week is It a shame because they getting nice deals on tokens. You can churn billions of tokens per month Just grow up already... reply Image 22giwook2 hours ago | root | parent | next[–] Unfortunately it takes years to grow up reply Image 23thegreatpeter24 minutes ago | parent | prev | next[–] crazy how quickly somebody's good will can erode with a post like this opencode team is great and dax doesn't even follow me reply Image 24skeptic_ai2 hours ago | parent | prev | next[–] I sent a support question and they don’t even know what exact models are running. lol reply Image 25aleqs1 hour ago | parent | prev | next[–] Yeah I've been somewhat disappointed with opencode lately (not as disappointed as I am in codex though)... the issues and PRs on GitHub are continuously accumulating and they don't seem to have any structured/efficient way to deal with it. Obvious issues with obvious fixes, and zero disagreement are sitting so long that they just get auto closed after 1 month. reply Image 26grandpajoey1 hour ago | parent | prev | next[–] You should probably disclose that you’ve launched a competitor to this product: https://news.ycombinator.com/favorites?id=testtestmetest reply Image 27testtestmetest1 hour ago | root | parent | next[–] Huh??? Why did you link my favorites.. Those aren't my submissions... Typical vibecoder lost his reading ability. Why are you doing oppo resesrch on me lol, I do not have any sort of product in the AI space lol. reply Image 28jeremyjacob3 hours ago | prev | next[–] The functionality seems to overlap with the Playwright MCP server [0]. I've been using this instead of the built in browsers in Claude Code and Codex since it lets you grant access to pages and sessions that are already open. Of course one should be weary of the lethal trifecta when using these tools and use separate profiles for them. [0] https://playwright.dev/docs/getting-started-mcp reply Image 29mrdw3 hours ago | parent | next[–] Also we have Chrome's official https://github.com/ChromeDevTools/chrome-devtools-mcp reply Image 30cyanydeez3 hours ago | parent | prev | next[–] I implemented this hard forking paseo. It's deferent; with a plugin in firefox, edge, chrome, chromium; I can bring an agent into it. Secure contexts like outlook I can have the agent scroll through my messages. Playwright won't (safely) get you these things. reply Image 31sixtyj3 hours ago | prev | next[–] > Your real browser: Chrome, Edge, Brave, Arc, Helium, Vivaldi, Opera and Chromium. Firefox not? reply Image 32skeledrew2 hours ago | parent | next[–] I made an extension a while back that fully exposes all of Firefox so it's CLI-accessible. It's actually not that much effort. reply Image 33guipsp3 hours ago | parent | prev | next[–] Well, it's an extension, so the api surface is different on FF. So it's not just a matter of them not listing it. reply Image 34goda903 hours ago | parent | prev | next[–] Looks like they only target Chromium-based browsers with their extension. reply Image 35damsta2 hours ago | parent | prev | next[–] And also Arc is dead reply Image 36mitchitized3 hours ago | parent | prev | next[–] It is a chromium extension and Firefox is not a chromium-based browser. Like or dislike Firefox, omitting it from a list called "real browser" just looks amateur or sloppy. How about "real chromium browser"? Was it really that hard? reply Image 37frizlab2 hours ago | parent | prev | next[–] Nor Safari reply Image 38warkdarrior3 hours ago | parent | prev | next[–] Firefox is not a real browser, it does not even support CDP. reply Image 39sunaookami18 minutes ago | root | parent | next[–] Now think about what the C in CDP means. reply Image 40kristopolous1 hour ago | prev | next[–] I was just looking into these "chat with ai agent about a webpage" browser extensions/projects/forks ... can someone help me sort out this field? it seems really busy. What I really want is like something that can search, use my own openai compatible server with, and I think that's it? I dunno what else these things do. reply Image 41mrdw3 hours ago | prev | next[–] why not https://github.com/ChromeDevTools/chrome-devtools-mcp reply Image 42pdp2 hours ago | prev | next[–] Cool.. but I think it is just simply better to give your AI agents their own browsers for your own sanity. reply Image 43skeledrew2 hours ago | prev | next[–] I found agent browsing to be an issue when I started using them months ago. Built a Firefox extension back then that uses the browser instance that I use, the way I use it, so there's really no difference to a site. reply Image 44orsenthil3 hours ago | prev | next[–] OpenCode comes with the cost too. The cost of the hosted version is on par with cloud hosted proprietary models. And we cannot simply run the LLMs on every laptop. Given this, how do we us the browse efficiently? reply Image 45oreally1 minute ago | parent | next[–] Yea it was a pity when opencode limited the token usage and told us to subscribe to their opencode go service. Like openai, it's clearly angling for commercial viability status under the guise of being 'open'. reply Image 46latentsea28 minutes ago | parent | prev | next[–] Just use the spare R9700 you have lying around and run locally. reply Image 47ekisu3 hours ago | parent | prev | next[–] you don't have to use their hosted models, nor their agent, for that matter was this comment made by literally looking at the url? XD reply Image 48bob102911 minutes ago | prev | next[–] I don't understand the need for this. A strong reasoning model already knows how to use Powershell to launch my browser with my profile. gpt-6.1-terra will build a whole goddamn .NET project with playwright just to pull the showtimes from the local cineplex. Shell execute and apply patch are the only two tools you need if your reasoning model is powerful enough. reply Image 49keyle24 minutes ago | prev | next[–] You had me, until "... your logins and your extensions". It's like open doors at a virus research facility. reply Image 50sans_souse28 minutes ago | prev | next[–] Check out https://opencode.ai/robots.txt for a treat reply Image 51breakwaterlabs2 hours ago | prev | next[–] At least they don't even pretend that it's sandboxed or approval gated. To anyone trying this, good luck and keep a fire extinguisher handy. reply Image 52vibebingo2 hours ago | prev | next[–] Oh this is a problem? I just ask my agent to do stuff with a browser and it figures it out. reply Image 53esafak3 hours ago | prev | next[–] It's all right when it works, but it has a habit of disconnecting; you have to rerun 'browse pair'. This MCP should hopefully become unnecessary once OpenCode's integrated browser tool gains persistent sessions. https://github.com/anomalyco/opencode/pull/63002 reply Image 54latchkey2 hours ago | prev[–] codex's extension connection will often randomly fail on me and i (and ai) can't figure out how to get it working again. i've switched to using omp's extension and that seems to work better. https://github.com/can1357/oh-my-pi/blob/main/packages/brows... reply Image 55 Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:

來源:Hacker News:AI 熱帖 · news.ycombinator.com